Triple
T8081522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tennessee-class battleship |
E188625
|
entity |
| Predicate | underwaterProtection |
P27649
|
FINISHED |
| Object | torpedo defense system |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: torpedo defense system | Statement: [Tennessee-class battleship, underwaterProtection, torpedo defense system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underwaterProtection Context triple: [Tennessee-class battleship, underwaterProtection, torpedo defense system]
-
A.
waterResistanceRating
Indicates the level to which something can resist water penetration or damage under specified conditions.
-
B.
protectiveEquipment
chosen
Indicates that one entity serves as protective equipment used to safeguard another entity from harm or risk.
-
C.
hasDivingComponent
Indicates that an activity, event, or process includes or involves a diving-related element or action.
-
D.
submergedBy
Indicates that one entity is covered or overwhelmed by liquid, typically water, to the point of being beneath its surface due to the action or presence of another entity.
-
E.
divingBehavior
Indicates the characteristic way an entity performs or exhibits diving actions, such as how, when, or how often it dives.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca82b662e88190b9323daab8c28a21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb40a699388190a5b8e26524ae43e5 |
completed | March 31, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69cb049f1614819087360d1a4c6f0faa |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:28 p.m.